Keras metadata

Keras metadata

Get metadata about a trained Keras block. Use the impulse blocks to find the learnId.

GEThttps://studio.edgeimpulse.com/v1/api/{projectId}/training/keras/{learnId}/metadata

Path parameters

projectId*integer

Project ID

learnId*integer

Learn Block ID, use the impulse functions to retrieve the ID

Response

200

OK

Body

application/json

success*boolean

Whether the operation succeeded

errorstring

Optional error description (set if 'success' was false)

created*string (date-time)

Date when the model was trained

layers*array of KerasModelLayer (object)

Layers of the neural network

classNames*array of string

Labels for the output layer

labels*array of string

Original labels in the dataset when features were generated, e.g. used to render the feature explorer.

availableModelTypes*array of KerasModelTypeEnum (enum)

The types of model that are available

recommendedModelType*KerasModelTypeEnum (enum)

int8float32akidarequiresRetrain

modelValidationMetrics*array of KerasModelMetadataMetrics (object)

Metrics for each of the available model types

hasTrainedModel*boolean

mode*KerasModelMode (enum)

classificationregressionobject-detectionvisual-anomalyanomaly-gmm

objectDetectionLastLayerObjectDetectionLastLayer (enum)

mobilenet-ssdfomoyolov2-akidayolov5yolov5v5-drpaiyoloxyolov7tao-retinanettao-ssdtao-yolov3tao-yolov4

imageInputScaling*ImageInputScaling (enum)

Normalization that is applied to images. If this is not set then 0..1 is used. "0..1" gives you non-normalized pixels between 0 and 1. "-1..1" gives you non-normalized pixels between -1 and 1. "0..255" gives you non-normalized pixels between 0 and 255. "-128..127" gives you non-normalized pixels between -128 and 127. "torch" first scales pixels between 0 and 1, then applies normalization using the ImageNet dataset (same as torchvision.transforms.Normalize()). "bgr-subtract-imagenet-mean" scales to 0..255, reorders pixels to BGR, and subtracts the ImageNet mean from each channel.

0..1-1..1-128..1270..255torchbgr-subtract-imagenet-mean

Request

JavaScriptCurl

const response = await fetch('https://studio.edgeimpulse.com/v1/api/{projectId}/training/keras/{learnId}/metadata', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

{
  "success": false,
  "error": "text",
  "created": "2024-07-04T17:38:05.984Z",
  "layers": [
    {
      "input": {
        "shape": 33,
        "name": "x_input:0",
        "type": "<dtype: 'float32'>"
      },
      "output": {
        "shape": 20,
        "name": "dense_1/Relu:0",
        "type": "<dtype: 'float32'>"
      }
    }
  ],
  "classNames": [
    "text"
  ],
  "labels": [
    "text"
  ],
  "availableModelTypes": [
    "int8"
  ],
  "recommendedModelType": "int8",
  "modelValidationMetrics": [
    {
      "type": "int8",
      "loss": 0,
      "accuracy": 0,
      "confusionMatrix": [
        [
          31,
          1,
          0
        ],
        [
          2,
          27,
          3
        ],
        [
          1,
          0,
          39
        ]
      ],
      "onDevicePerformance": [
        {
          "mcu": "text",
          "name": "text",
          "isDefault": false,
          "latency": 0,
          "tflite": {},
          "eon": {},
          "eon_ram_optimized": {},
          "customMetrics": [
            {
              "name": "text",
              "value": "text"
            }
          ]
        }
      ],
      "predictions": [
        {
          "startMs": 0,
          "endMs": 0,
          "label": "text",
          "prediction": "text",
          "predictionCorrect": false,
          "f1Score": 0,
          "anomalyScores": [
            [
              0
            ]
          ]
        }
      ],
      "visualization": "featureExplorer",
      "isSupportedOnMcu": false,
      "mcuSupportError": "text",
      "profilingJobFailed": false,
      "additionalMetrics": [
        {
          "name": "text",
          "value": "text",
          "tooltipText": "text",
          "link": "text"
        }
      ]
    }
  ],
  "hasTrainedModel": false,
  "mode": "classification",
  "objectDetectionLastLayer": "mobilenet-ssd",
  "imageInputScaling": "0..1"
}